Python base.ClassifierMixin方法代码示例

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_base_chain_fit_and_predict():
    # Fit base chain and verify predict performance
    X, Y = generate_multilabel_dataset_with_correlations()
    chains = [RegressorChain(Ridge()),
              ClassifierChain(LogisticRegression())]
    for chain in chains:
        chain.fit(X, Y)
        Y_pred = chain.predict(X)
        assert_equal(Y_pred.shape, Y.shape)
        assert_equal([c.coef_.size for c in chain.estimators_],
                     list(range(X.shape[1], X.shape[1] + Y.shape[1])))

    Y_prob = chains[1].predict_proba(X)
    Y_binary = (Y_prob >= .5)
    assert_array_equal(Y_binary, Y_pred)

    assert isinstance(chains[1], ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def __init__(self, classifier=None, predictors="all"):
        """Create an instance of the MissingnessClassifier.

        The MissingnessClassifier inherits from sklearn BaseEstimator and
        ClassifierMixin. This inheritence and this class' implementation
        ensure that the MissingnessClassifier is a valid classifier that will
        work in an sklearn pipeline.

        Args:
            classifier (classifier, optional): valid classifier from sklearn.
                If None, default is xgboost. Note that classifier must
                conform to sklearn style. This means it must implement the
                `predict_proba` method and act as a porper classifier.
            predictors (str, iter, dict, optiona): defaults to all, i.e.
                use all predictors. If all, every column will be used for
                every class prediction. If a list, subset of columns used for
                all predictions. If a dict, specify which columns to use as
                predictors for each imputation. Columns not specified in dict
                will receive `all` by default.
        """
        self.classifier = classifier
        self.predictors = predictors 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_template_1():
    """Assert that TPOT template option generates pipeline when each step is a type of operator."""

    tpot_obj = TPOTClassifier(
        random_state=42,
        verbosity=0,
        template='Selector-Transformer-Classifier'
    )
    tpot_obj._fit_init()
    pop = tpot_obj._toolbox.population(n=10)
    for deap_pipeline in pop:
        operator_count = tpot_obj._operator_count(deap_pipeline)
        sklearn_pipeline = tpot_obj._toolbox.compile(expr=deap_pipeline)
        assert operator_count == 3
        assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[1][1].__class__, TransformerMixin)
        assert issubclass(sklearn_pipeline.steps[2][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_template_2():
    """Assert that TPOT template option generates pipeline when each step is operator type with a duplicate main type."""

    tpot_obj = TPOTClassifier(
        random_state=42,
        verbosity=0,
        template='Selector-Selector-Transformer-Classifier'
    )
    tpot_obj._fit_init()
    pop = tpot_obj._toolbox.population(n=10)
    for deap_pipeline in pop:
        operator_count = tpot_obj._operator_count(deap_pipeline)
        sklearn_pipeline = tpot_obj._toolbox.compile(expr=deap_pipeline)
        assert operator_count == 4
        assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[1][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[2][1].__class__, TransformerMixin)
        assert issubclass(sklearn_pipeline.steps[3][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_template_3():
    """Assert that TPOT template option generates pipeline when one of steps is a specific operator."""

    tpot_obj = TPOTClassifier(
        random_state=42,
        verbosity=0,
        template='SelectPercentile-Transformer-Classifier'
    )
    tpot_obj._fit_init()
    pop = tpot_obj._toolbox.population(n=10)
    for deap_pipeline in pop:
        operator_count = tpot_obj._operator_count(deap_pipeline)
        sklearn_pipeline = tpot_obj._toolbox.compile(expr=deap_pipeline)
        assert operator_count == 3
        assert sklearn_pipeline.steps[0][0] == 'SelectPercentile'.lower()
        assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[1][1].__class__, TransformerMixin)
        assert issubclass(sklearn_pipeline.steps[2][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_template_4():
    """Assert that TPOT template option generates pipeline when one of steps is a specific operator."""

    tpot_obj = TPOTClassifier(
        population_size=5,
        generations=2,
        random_state=42,
        verbosity=0,
        config_dict = 'TPOT light',
        template='SelectPercentile-Transformer-Classifier'
    )
    tpot_obj.fit(pretest_X, pretest_y)

    assert isinstance(tpot_obj._optimized_pipeline, creator.Individual)
    assert not (tpot_obj._start_datetime is None)

    sklearn_pipeline = tpot_obj.fitted_pipeline_
    operator_count = tpot_obj._operator_count(tpot_obj._optimized_pipeline)
    assert operator_count == 3
    assert sklearn_pipeline.steps[0][0] == 'SelectPercentile'.lower()
    assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
    assert issubclass(sklearn_pipeline.steps[1][1].__class__, TransformerMixin)
    assert issubclass(sklearn_pipeline.steps[2][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def _get_child_predict(self, clf, X, index=None):
        if self.stack_by_proba and hasattr(clf, 'predict_proba'):
            if self.save_stage0 and index is not None:
                proba = util.saving_predict_proba(clf, X, index)
            else:
                proba = clf.predict_proba(X)
            return proba[:, 1:]
        elif hasattr(clf, 'predict'):
            predict_result = clf.predict(X)
            if isinstance(clf, ClassifierMixin):
                lb = LabelBinarizer()
                lb.fit(predict_result)
                return lb.fit_transform(predict_result)
            else:
                return predict_result.reshape((predict_result.size, 1))
        else:
            return clf.fit_transform(X) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_classifier_chain_fit_and_predict_with_logistic_regression():
    # Fit classifier chain and verify predict performance
    X, Y = generate_multilabel_dataset_with_correlations()
    classifier_chain = ClassifierChain(LogisticRegression())
    classifier_chain.fit(X, Y)

    Y_pred = classifier_chain.predict(X)
    assert_equal(Y_pred.shape, Y.shape)

    Y_prob = classifier_chain.predict_proba(X)
    Y_binary = (Y_prob >= .5)
    assert_array_equal(Y_binary, Y_pred)

    assert_equal([c.coef_.size for c in classifier_chain.estimators_],
                 list(range(X.shape[1], X.shape[1] + Y.shape[1])))

    assert isinstance(classifier_chain, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_sample_weight():
    """Tests sample_weight parameter of VotingClassifier"""
    clf1 = LogisticRegression(random_state=123)
    clf2 = RandomForestClassifier(random_state=123)
    clf3 = SVC(gamma='scale', probability=True, random_state=123)
    eclf1 = VotingClassifier(estimators=[
        ('lr', clf1), ('rf', clf2), ('svc', clf3)],
        voting='soft').fit(X, y, sample_weight=np.ones((len(y),)))
    eclf2 = VotingClassifier(estimators=[
        ('lr', clf1), ('rf', clf2), ('svc', clf3)],
        voting='soft').fit(X, y)
    assert_array_equal(eclf1.predict(X), eclf2.predict(X))
    assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))

    sample_weight = np.random.RandomState(123).uniform(size=(len(y),))
    eclf3 = VotingClassifier(estimators=[('lr', clf1)], voting='soft')
    eclf3.fit(X, y, sample_weight)
    clf1.fit(X, y, sample_weight)
    assert_array_equal(eclf3.predict(X), clf1.predict(X))
    assert_array_almost_equal(eclf3.predict_proba(X), clf1.predict_proba(X))

    # check that an error is raised and indicative if sample_weight is not
    # supported.
    clf4 = KNeighborsClassifier()
    eclf3 = VotingClassifier(estimators=[
        ('lr', clf1), ('svc', clf3), ('knn', clf4)],
        voting='soft')
    msg = ('Underlying estimator KNeighborsClassifier does not support '
           'sample weights.')
    with pytest.raises(ValueError, match=msg):
        eclf3.fit(X, y, sample_weight)

    # check that _parallel_fit_estimator will raise the right error
    # it should raise the original error if this is not linked to sample_weight
    class ClassifierErrorFit(BaseEstimator, ClassifierMixin):
        def fit(self, X, y, sample_weight):
            raise TypeError('Error unrelated to sample_weight.')
    clf = ClassifierErrorFit()
    with pytest.raises(TypeError, match='Error unrelated to sample_weight'):
        clf.fit(X, y, sample_weight=sample_weight) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def test_sample_weight_kwargs():
    """Check that VotingClassifier passes sample_weight as kwargs"""
    class MockClassifier(BaseEstimator, ClassifierMixin):
        """Mock Classifier to check that sample_weight is received as kwargs"""
        def fit(self, X, y, *args, **sample_weight):
            assert 'sample_weight' in sample_weight

    clf = MockClassifier()
    eclf = VotingClassifier(estimators=[('mock', clf)], voting='soft')

    # Should not raise an error.
    eclf.fit(X, y, sample_weight=np.ones((len(y),))) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def _generate_bases_test(est, pd_est):
    def test(self):
        self.assertTrue(isinstance(pd_est, FrameMixin), pd_est)
        self.assertFalse(isinstance(est, FrameMixin))
        self.assertTrue(isinstance(pd_est, base.BaseEstimator))
        try:
            mixins = [
                base.ClassifierMixin,
                base.ClusterMixin,
                base.BiclusterMixin,
                base.TransformerMixin,
                base.DensityMixin,
                base.MetaEstimatorMixin,
                base.ClassifierMixin,
                base.RegressorMixin]
        except:
            if _sklearn_ver > 17:
                raise
            mixins = [
                base.ClassifierMixin,
                base.ClusterMixin,
                base.BiclusterMixin,
                base.TransformerMixin,
                base.MetaEstimatorMixin,
                base.ClassifierMixin,
                base.RegressorMixin]
        for mixin in mixins:
            self.assertEqual(
                isinstance(pd_est, mixin),
                isinstance(est, mixin),
                mixin)

    return test 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def _exposed_methods_mapping(self) -> Dict[str, str]:
        ret = {
            'predict': 'predict'
        }
        if isinstance(self.model, ClassifierMixin):
            ret['predict_proba'] = 'predict_proba'
        return ret 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def transform(self, X):
        X = check_array(X)
        X_transformed = np.copy(X)
        # add class probabilities as a synthetic feature
        if issubclass(self.estimator.__class__, ClassifierMixin) and hasattr(self.estimator, 'predict_proba'):
            X_transformed = np.hstack((self.estimator.predict_proba(X), X))

        # add class prodiction as a synthetic feature
        X_transformed = np.hstack((np.reshape(self.estimator.predict(X), (-1, 1)), X_transformed))

        return X_transformed 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def transform(self, X):
        """Transform data by adding two synthetic feature(s).

        Parameters
        ----------
        X: numpy ndarray, {n_samples, n_components}
            New data, where n_samples is the number of samples and n_components is the number of components.

        Returns
        -------
        X_transformed: array-like, shape (n_samples, n_features + 1) or (n_samples, n_features + 1 + n_classes) for classifier with predict_proba attribute
            The transformed feature set.
        """
        X = check_array(X)
        X_transformed = np.copy(X)
        # add class probabilities as a synthetic feature
        if issubclass(self.estimator.__class__, ClassifierMixin) and hasattr(self.estimator, 'predict_proba'):
            y_pred_proba = self.estimator.predict_proba(X)
            # check all values that should be not infinity or not NAN
            if np.all(np.isfinite(y_pred_proba)):
                X_transformed = np.hstack((y_pred_proba, X))

        # add class prediction as a synthetic feature
        X_transformed = np.hstack((np.reshape(self.estimator.predict(X), (-1, 1)), X_transformed))

        return X_transformed 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import ClassifierMixin [as 别名]
def score(self, X, y):
        """Force use of accuracy score since we don't inherit
           from ClassifierMixin"""

        from sklearn.metrics import accuracy_score
        return accuracy_score(y, self.predict(X))